Search Everything

Tip: Search using "First Name + Last Name", e.g.
János Kiss instead of Kiss János.

Publications - 6383

Classification of Time Series Using Singular Values and Wavelet Subband Analysis with ANN and SVM Classifiers

Balázs Benyó Péter Somogyi Béla Paláncz

Publication Name: Journal of Advanced Computational Intelligence and Intelligent Informatics

Publication Date: 2006-07-01

Volume: 10

Issue: 4

Page Range: 498-503

Description:

Oscillation of cerebral blood flow (CBF) in physiological or pathophysiological brain states is common, therefore it is promising to identify cerebral circulation disorders based on CBF signal classification. To characterize temporal blood flow patterns, we applied two feature extractions, spectral matrix and wavelet subband analysis. To distinguish between different physiological states, two different classifications have been developed – the radial basis function-based neural network and a support vector classifier with a Gaussian kernel. Feature extraction and classification are evaluated and their efficiency compared. Calculation was done using Mathematica 5.1 and its Wavelet Application.

Open Access: Yes

DOI: 10.20965/jaciii.2006.p0498

Land-use zone estimation in public transport planning with data mining

Richárd Horváth Balázs Horváth Viktor Nagy

Publication Name: Transportation Research Procedia

Publication Date: 2017-01-01

Volume: 27

Issue: Unknown

Page Range: 1050-1057

Description:

Nowadays, data sets are spreading continually, generated by different devices and systems. The modern GPS based tracking systems and the electronic tickets are producing lots of data, and we could use them, for improving the service level. These data are processable with the modern devices and methods, and we can use them for obtaining information. Thanks to the spread of data mining, these tools are not appearing only in marketing research, but also in the most various kind of scientific areas and they are advertising a new scientific revolution. Although the importance of these data sources is essential it is not widespread in transport planning except in some specific areas. The smart card systems store the number of boarding passengers and in some cases also the alighting values. From the passengers' boarding and alighting information in a stop point we can create a time series, which shows the behavior type of the given stop points presented on graphic curves. With the help of different clustering and classification processes, these curves can be turned into groups and we can observe these groups of stop points which are defining separated zones. This is the basic step in transport modelling and the zones were determined by manual methods usually. In this paper we examine clustering and classification methods compared to each other and check the usability of different distance measurement techniques. This paper shows the usage of these methods in public transportation and presents the background of this kind of zone distribution technic.

Open Access: Yes

DOI: 10.1016/j.trpro.2017.12.145

Anisotropic vector hysteresis model applying Everett function and neural network

Amália Iványi Miklós Kuczmann

Publication Name: Physica B Condensed Matter

Publication Date: 2006-02-01

Volume: 372

Issue: 1-2

Page Range: 138-142

Description:

This paper deals with a simulation technique based on neural networks and an identification method to approximate the behavior of vector hysteresis characteristics of ferromagnetic materials. The identification procedure is based on theoretical measured vector Everett functions using Fourier expansion to deal with angle dependence of the measured scalar Everett functions and of the vector Everett functions in the 2D or in the 3D space. Computing afterwards the theoretical measured vector Everett functions for some given directions, the corresponding hysteresis models are approximated by neural networks and are used to build up the vectorial hysteresis model both in isotropic and anisotropic case. The properties of the anisotropic model has been analyzed and shown in figures. For some examples, the first order reversal curves determined from the vectorial model are compared with the corresponding measured curves that have been used to compute the measured scalar Everett functions being the input for the identification procedure. © 2005 Elsevier B.V. All rights reserved.

Open Access: Yes

DOI: 10.1016/j.physb.2005.10.034

Expanded scope of traffic-flow analysis: Entity flow-phase analysis for rapid performance evaluation of enterprise process systems

László Muka G. Lencse

Publication Name: Esm 2006 2006 European Simulation and Modelling Conference Modelling and Simulation 2006

Publication Date: 2006-01-01

Volume: Unknown

Issue: Unknown

Page Range: 94-98

Description:

This paper describes entity-flow phase analysis (EFA) which is a method for fast performance analysis of organisational process systems. EFA, similarly to traffic-flow analysis for communication systems (TFA), uses the combined approach of simulation and numerical methods. In simulation projects initiated to support the design of Information and Communication Technology (ICT) system and Business Process (BP) system in an organisation the parallel analysis of different systems may be efficient. EFA is a promising evaluation method to be applied for systems with determined BP and ICT subsystems in an organisational environment.

Open Access: Yes

DOI: DOI not available

Sustainability Factors of Cultural and Creative Industries - The Case Study of a Creative City, Budapest

Petra Kinga Kézai Szandra Gombos

Publication Name: Chemical Engineering Transactions

Publication Date: 2023-01-01

Volume: 107

Issue: Unknown

Page Range: 127-132

Description:

Regarding Cultural and Creative Industries (CCI) concept-related development, an important aspect has arisen and become inevitable in the last few years: sustainability. Although sustainability and creativity are closely linked, it is important to examine the sustainability factors of creative city development from a broader perspective. The present research aims to explore the environmental sustainability of the cultural and creative industry of a Central and Eastern European capital, Budapest, through a literature review and then two case studies of environmentally sustainable CCI companies. The aim of the paper is to show the gap in the literature regarding the environmental sustainability of the CCI sector, despite its significance, and present two case studies of how environmental sustainability can appear in two CCI companies, showing a best practice. The literature analysis has shown that the interpretation of CCIs' sustainability and the comparability of the sector in the region under study are hampered by the wide variation in methodologies for measuring the sustainability of CCIs. In the case of Budapest, within the study’s 13 y reach, research has shown that Budapest plays a significant role in CCIs, although it also struggles with the issues of sustainability. The two case studies can show role models for environmentally sustainable CCIs by making sustainability the scope and basis of their operation.

Open Access: Yes

DOI: 10.3303/CET23107022

A distance model for safety-critical systems

Miklós Szijártó Gábor Kallos Dietmár Gröger

Publication Name: Periodica Polytechnica Electrical Engineering

Publication Date: 2001-01-01

Volume: 45

Issue: 2

Page Range: 109-118

Description:

In this paper we introduce a new, theoretical model for safety-critical systems in which the distance from the dangerous conditions can be measured. To describe these systems we use besides the graph model Petri nets, too. We illustrate the theoretical discussion with some simple examples.

Open Access: Yes

DOI: DOI not available

Sentinels of Sustainability: Practices of Agricultural Farms Clustered in Hungary’s Farmers’ Markets

Károly Kacz Koltai Judit Petra Szabolcs Troján Tamás Vinkóczi Anita Miklósné Varga

Publication Name: Chemical Engineering Transactions

Publication Date: 2024-01-01

Volume: 114

Issue: Unknown

Page Range: 973-978

Description:

The analysis of local farmers' markets (FMs) is an important part of sustainability issues, as the products they offer can guarantee both the proper functioning of local farms and healthy nutrition for inhabitants. The aim of this research is to identify the most important characteristics of FMs small-scale businesses related to agricultural activities based on a convenience sample in Hungary. The database obtained by the questionnaire survey was compiled based on the answers of a total of 220 farm owners/managers. The results were subjected to analysis using a K-means clustering method, which identified four distinct groups of farms with the highest weighting of turnover from agricultural activity. The clustering distinguished beekeeping, arable crop production, animal husbandry, and vegetable and fruit production, which were treated as a separate cluster. The observed differences between the groups indicate that farms primarily engaged in beekeeping and livestock farming have the highest turnover. These findings may be manifested by the group’s member farms in terms of higher professional representation and high-quality products. A noteworthy distribution-related finding is that livestock products exhibit the greatest average distance from the point of origin to the FM, which can be attributed to the sparse geographical location of the production sites. The results could have a considerable consequence for policymakers in informing them about the design of support opportunities and the identification of beneficiary groups.

Open Access: Yes

DOI: 10.3303/CET24114163

Comparison of Extended and Unscented Kalman Filters with and without Using Mechanical Model for Speed Sensorless Control of Induction Machines

Krisztián Horváth

Publication Name: 2023 18th Conference on Electrical Machines Drives and Power Systems Elma 2023 Proceedings

Publication Date: 2023-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

In this work, speed sensorless state estimators are compared for induction machine drives. The studied estimators are based on two widely used state-space models. The first one has five state variables and assumes slowly varying rotor speed. In contrast, the second model is augmented by the equation of motion and the load torque is defined as an additional state variable. Due to the nonlinearities, extended and unscented Kalman filters are applied in the case of both models. To compare the parameter sensitivities and the low speed operation of the four state estimators, simulations and experiments are carried out. In addition, the estimators are also tested in speed sensorless closed-loop control structure.

Open Access: Yes

DOI: 10.1109/ELMA58392.2023.10202302

An efficient evolutionary metaheuristic for the traveling repairman (Minimum latency) problem

Péter Földesi Boldizsár Tüű-Szabó László T. Kóczy

Publication Name: International Journal of Computational Intelligence Systems

Publication Date: 2020-01-01

Volume: 13

Issue: 1

Page Range: 781-793

Description:

In this paper we revisit the memetic evolutionary family of metaheuristics, called Discrete Bacterial Memetic Evolutionary Algorithm (DBMEA), whose members combine Furuhashi’s Bacterial Evolutionary Algorithm and various discrete local search techniques. These algorithms have proven to be efficient approaches for the solution of NP-hard discrete optimization problems such as the Traveling Salesman Problem (TSP) with Time Windows. This paper presents our results in solving the Traveling Repairman Problem (also called Minimum Latency Problem) with a DBMEA variant. The results are compared with state-of-the-art heuristics found in the literature. The DBMEA in most cases turned out to be faster than all other methods, and for the bigger benchmark instances it was also found to have better solutions than the former best-known results. Based on these test results we claim to have found the best approach and thus we suggest the use of the DBMEA for the Traveling Repairman Problem, especially for large instances.

Open Access: Yes

DOI: 10.2991/ijcis.d.200529.001